© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6285
    Prev
    Next
    INDEX
    Explanations

    excited

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ೊ
    -0.46
     vertes
    -0.46
     biais
    -0.46
     triliun
    -0.46
    "/>
    -0.45
     istr
    -0.44
     waking
    -0.44
    )}</
    -0.44
     optique
    -0.44
     realising
    -0.43
    POSITIVE LOGITS
     for
    0.72
    SourceChecksum
    0.63
    for
    0.62
    หรับ
    0.60
    ManagedBean
    0.59
    urée
    0.57
     سكانية
    0.56
    èdia
    0.55
    جمعیت
    0.54
     для
    0.54
    Activations Density 0.002%

    No Known Activations